✨ chore(model-bank): backfill knowledgeCutoff + family/generation data (#15642)

* ✨ feat(model-bank): backfill knowledgeCutoff for OpenAI/Claude/Llama/Phi families (batch 1)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* ✨ feat(model-bank): add family/generation fields with rule-derived data for chat models

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* ✨ feat(model-bank): add canonical knowledge-cutoff map with build-time backfill

Adds MODEL_KNOWLEDGE_CUTOFFS (canonical id → YYYY-MM, all values verified
against official provider docs) plus normalizeModelIdForCutoff, which reduces
provider-specific spellings (openrouter/bedrock prefixes, dated snapshots,
-thinking/-fast/-latest/-preview variants, claude dot-versions) to canonical
ids. buildDefaultModelList backfills knowledgeCutoff from the map when a model
card has no inline value, so all aggregator providers inherit cutoffs
automatically; inline values always win.

Covers Anthropic (incl. legacy 3.x), OpenAI, Google Gemini/Gemma, xAI Grok,
Meta Llama, Amazon Nova, and Cohere. DeepSeek/Qwen/GLM/Kimi/MiniMax/Mistral
publish no official cutoffs and are intentionally absent. Anthropic inline
PoC entries migrate into the map (single source of truth).

Cross-checked against the batch-1 inline backfill: 0 value mismatches.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* 🐛 fix(model-bank): correct Claude Sonnet 4.6 cutoff

* ✅ test(model-bank): sync metadata expectations

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>

apps/server/src/routers/lambda/config/__snapshots__/index.test.ts.snap

@@ -31,7 +31,10 @@ exports[`configRouter > getGlobalConfig > Model Provider env > OPENAI_MODEL_LIST
       "description": "The latest GPT-4 Turbo model includes vision. Vision requests can use JSON mode and function calling. GPT-4 Turbo is an enhanced version that balances accuracy and efficiency for cost-effective multimodal tasks and real-time interactions.",
       "displayName": "gpt-4-32k",
       "enabled": true,
+      "family": "gpt",
+      "generation": "gpt-4",
       "id": "gpt-4-0125-preview",
+      "knowledgeCutoff": undefined,
       "pricing": {
         "units": [
           {
@@ -66,7 +69,10 @@ exports[`configRouter > getGlobalConfig > Model Provider env > OPENAI_MODEL_LIST
     "description": "GPT 3.5 Turbo for text generation and understanding; currently points to gpt-3.5-turbo-0125.",
     "displayName": "GPT-3.5 Turbo 1106",
     "enabled": true,
+    "family": "gpt",
+    "generation": "gpt-3.5",
     "id": "gpt-3.5-turbo-1106",
+    "knowledgeCutoff": undefined,
     "pricing": {
       "units": [
         {
@@ -96,7 +102,10 @@ exports[`configRouter > getGlobalConfig > Model Provider env > OPENAI_MODEL_LIST
     "description": "GPT 3.5 Turbo for text generation and understanding; currently points to gpt-3.5-turbo-0125.",
     "displayName": "GPT-3.5 Turbo",
     "enabled": true,
+    "family": "gpt",
+    "generation": "gpt-3.5",
     "id": "gpt-3.5-turbo",
+    "knowledgeCutoff": "2021-09",
     "pricing": {
       "units": [
         {
@@ -125,7 +134,10 @@ exports[`configRouter > getGlobalConfig > Model Provider env > OPENAI_MODEL_LIST
     "description": "GPT-4 provides a larger context window to handle longer inputs, suitable for broad information synthesis and data analysis.",
     "displayName": "GPT-4",
     "enabled": true,
+    "family": "gpt",
+    "generation": "gpt-4",
     "id": "gpt-4",
+    "knowledgeCutoff": "2023-12",
     "pricing": {
       "units": [
         {
@@ -154,7 +166,10 @@ exports[`configRouter > getGlobalConfig > Model Provider env > OPENAI_MODEL_LIST
     "description": "GPT-4 provides a larger context window to handle longer inputs for scenarios needing broad information integration and data analysis.",
     "displayName": "GPT-4 32K",
     "enabled": true,
+    "family": "gpt",
+    "generation": "gpt-4",
     "id": "gpt-4-32k",
+    "knowledgeCutoff": undefined,
     "pricing": {
       "units": [
         {
@@ -183,7 +198,10 @@ exports[`configRouter > getGlobalConfig > Model Provider env > OPENAI_MODEL_LIST
     "description": "The latest GPT-4 Turbo model includes vision. Vision requests can use JSON mode and function calling. GPT-4 Turbo is an enhanced version that balances accuracy and efficiency for cost-effective multimodal tasks and real-time interactions.",
     "displayName": "GPT-4 Turbo Preview 1106",
     "enabled": true,
+    "family": "gpt",
+    "generation": "gpt-4",
     "id": "gpt-4-1106-preview",
+    "knowledgeCutoff": undefined,
     "pricing": {
       "units": [
         {
@@ -223,7 +241,10 @@ exports[`configRouter > getGlobalConfig > Model Provider env > OPENAI_MODEL_LIST
   "description": "The latest GPT-4 Turbo model includes vision. Vision requests can use JSON mode and function calling. GPT-4 Turbo is an enhanced version that balances accuracy and efficiency for cost-effective multimodal tasks and real-time interactions.",
   "displayName": "GPT-4 Turbo Preview 1106",
   "enabled": true,
+  "family": "gpt",
+  "generation": "gpt-4",
   "id": "gpt-4-1106-preview",
+  "knowledgeCutoff": undefined,
   "pricing": {
     "units": [
       {